Piyuan Lin

Learn More
Question classification plays a crucial important role in the question answering system because categorizing a given question is beneficial to identify an answer in the documents. The goal of question classification is to accurately assign labels to question based on expected answer type. Support vector machines (SVMs) have been proved as an excellent tool(More)
More and more Chinese users express their views through Micro-blogging service during the rapid growth of the Internet today. Clustering these short Chinese texts to get knowledge automatically is an important field for many companies and governments. Because of 140 characters limit, users present any information with only a few words. Considering the view(More)
Forecasting the price of chicken plays a crucial important role in the poultry raising industry because it is beneficial to maximize the profit and minimize the risk. Its goal is to accurately predict the price in future based on the data obtained. ARMA is the classical time series prediction method and wavelet transform is well known to work well for(More)
Service Science is proposed as an integrative discipline with the purpose of creating new technology and market for providing high value service. The development of modern service industry urgently necessitates a new generation network and information supporting platform. This paper proposes an IT platform converging Grid and Cloud, which emphasizes(More)
To counter the problems existing in the process of object-oriented analysis and design teaching, the application necessity of the society and the status of the present IT intellectuals, this article points out a method of elicitation teaching for object-oriented analysis and design curriculum. And after application, the result shows that it can sufficiency(More)
This paper presents our valence-arousal (VA) prediction method in the IALP 2016 Shared Task of Dimensional Sentiment Analysis for Chinese Words. Dimensional approach represents affective states as continuous numerical values in multiple dimensions, such as the VA space, thus allowing for more fine-grained sentiment analysis. For VA prediction, existing(More)